云计算实验报告 - 图文(5)

（4） 在eclipse中编译好源代码后，导出程序的jar包，供在集群上使用。

2.在集群上运行程序

（1） 启动集群，通过jps命令查看master，slave上启动的服务列表，结果如

下：

（2） 在集群环境下运行该程序jar包（UserNameCount.jar），结果如下：

（3） 查看集群环境下启动程序生成的结果，即output文件，结果如下：

（4） 数据统计结果在part-r-00000中，具体内容如下，

7、源代码：

package hadoop;

import java.io.IOException;

import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.input.TextInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class UserNameCount {

public static class UserNameCountMap extends

Mapper {

private final IntWritable one = new IntWritable(1); private Text word = new Text();

public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { String line = value.toString();

StringTokenizer token = new StringTokenizer(line); while (token.hasMoreTokens()) { word.set(token.nextToken()); context.write(word, one); } } }

public static class UserNameCountReduce extends

Reducer {

public void reduce(Text key, Iterable values,

Context context) throws IOException, InterruptedException { int sum = 0;

for (IntWritable val : values) { sum += val.get(); }

context.write(key, new IntWritable(sum)); } }

public static void main(String[] args) throws Exception {

}

Configuration conf = new Configuration(); Job job = new Job(conf);

job.setJarByClass(UserNameCount.class); job.setJobName(\

job.setOutputKeyClass(Text.class);

job.setOutputValueClass(IntWritable.class); job.setMapperClass(UserNameCountMap.class); job.setReducerClass(UserNameCountReduce.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class);

FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.waitForCompletion(true); }